Cell culture experiment system, cell culture experiment method, and program

Abstract

To shorten a period until an appropriate environmental parameter is obtained in a cell culture experiment.SOLUTION: According to the present invention, a control device sets a recipe for each cell sample, and controls a robot device to perform a culture experiment according to the recipe. A database device sequentially stores intermediate progress data for each sample during one culture experiment in which a culture result is determined. A recipe determination device analyzes tendencies of the culture on the basis of the intermediate progress data for each sample, and on the basis of the analysis result and the difference in time-series intermediate progress data for the sample, calculates a posterior probability indicating a degree of probability leading to future success of the culture, with respect to values of a plurality of environmental parameters making up the recipe being set. The recipe determination device uses one or more environmental parameters having a relatively high posterior probability as a verification parameter, and modifies the value of the verification parameter for each sample to correct the recipe. The control device controls the robot device such that the experiment is continued according to the corrected recipe.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a cell culture experimental system, a cell culture experimental method, and a program. [Background technology]

[0002] In the life science industry, modalities such as regenerative medicine and cell manufacturing are still in their infancy. There are various disturbing factors before researchers can obtain the normal cells they desire, and it is necessary to conduct a huge number of repeated experiments at once before searching for the appropriate intermediate environmental parameters. The set of environmental parameters for manufacturing or culturing cells is also called a recipe.

[0003] Bayesian experimental design is known as a general method used in experiments for producing or culturing such cells. For example, Patent Document 1 describes a method for predicting one or more types of execution parameter items and their search ranges that may affect evaluation results based on one or more types of past execution results and evaluation results in a cell culture experiment, based on a given feature extraction rule, and generating multiple variable parameter values ​​included in the search range according to Bayesian optimization or the like, based on one or more types of past execution results and evaluation results. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2023-035238 A Summary of the Invention [Problem to be solved by the invention]

[0005] In Bayesian experimental design, the results of an experiment can be used to plan the next experiment, reducing the number of experiments to be performed, i.e., the amount of data required for the experiment, and thus improving the efficiency of the experiment. However, in Bayesian experimental design, the next experiment cannot be planned until the results of the experiment are obtained, and the time required for the experiment itself cannot be shortened. For example, it takes a long time, for example about four months, from the start of cell culture until the result is determined to be normal, and this period cannot be shortened.

[0006] For this reason, it takes four months to obtain accurate results and learn the appropriate intermediate environment parameters, and in principle it takes another four months before the next results can be obtained using the learned intermediate environment parameters, which is a factor that significantly reduces research efficiency. Even if the search period is effectively shortened by conducting a huge number of experiments at once, each experiment must be started in order according to the priority of the experiment.

[0007] An object of the present invention is to shorten the time required to obtain suitable environmental parameters in cell culture experiments. [Means for solving the problem]

[0008] One representative embodiment of the present invention includes a recipe judgment device that sets a recipe to be applied to each of a plurality of cell samples to be cultured, a robot device, a control device that controls the operation of the robot device so that the robot device performs a culture experiment on the plurality of samples according to the set recipe, and a database device in which interim data for each of the plurality of samples is stored in chronological order during one culture experiment in which the culture results of the plurality of samples are determined, and the recipe judgment device analyzes the tendency of the culture of each of the samples based on the interim data for each of the samples stored in the database device, and determines, for each of the samples, the tendency of the culture of the sample. This cell culture experimental system calculates a posterior probability indicating the degree of possibility that the parameter values ​​of multiple environmental parameters constituting the set recipe will cause future successful cultivation of the sample based on the trend analysis results and the difference in the time-series intermediate data of the sample, determines one or more of the environmental parameters with a relatively high calculated posterior probability as verification parameters, modifies the recipe for each sample by changing the parameter values ​​of the determined verification parameters, and the control device controls the operation of the robotic device so that the robotic device continues to perform the multiple culture experiments in accordance with the modified recipe.

[0009] A representative embodiment of the present invention is a cell culture experiment method, in which a recipe judgment device sets recipes to be applied to each of a plurality of samples of cells to be cultured, a control device controls the operation of the robot device so that the robot device performs a culture experiment of the plurality of samples according to the set recipe, a database device chronologically stores intermediate data for each of the samples during one culture experiment in which culture results of the plurality of samples are determined, the recipe judgment device analyzes a trend in the culture of each of the samples based on the intermediate data for each of the samples stored in the database device, and calculates, for each of the samples, a posterior probability representing a degree of possibility that a parameter value of a plurality of environmental parameters constituting the set recipe will cause future success in the culture of the sample based on a difference between a result of the analysis of the trend in the culture of the sample and the intermediate data of the sample in chronological order, determines one or more of the environmental parameters with a relatively high calculated posterior probability as a verification parameter, modifies the recipe for each of the samples by changing the parameter value of the determined verification parameter, and the control device controls the operation of the robot device so that the robot device continues to perform the plurality of culture experiments according to the modified recipe.

[0010] One representative embodiment of the present invention is a program for causing one or more computers or processors to function as a recipe judgment device that sets a recipe to be applied to each of a plurality of samples of cells to be cultured, a control device that controls the operation of the robot device so that the robot device performs a culture experiment of the plurality of samples according to the set recipe, and a database device that stores intermediate data for each of the samples in chronological order during one culture experiment in which the culture results of the plurality of samples are determined, the recipe judgment device analyzes the tendency in the culture of each of the samples based on the intermediate data for each of the samples stored in the database device, and the program calculates, for each of the experiments, a posterior probability indicating the degree of possibility that the parameter values ​​of the multiple environmental parameters constituting the set recipe will cause future success in culturing the sample based on the analysis results of the trend in culturing the sample and the difference in the chronological progress data of the sample, determines one or more of the environmental parameters for which the calculated posterior probability is relatively high as verification parameters, modifies the recipe for each of the samples by changing the parameter values ​​of the determined verification parameters, and the control device controls the operation of the robotic device so that the robotic device continues to perform the multiple culture experiments in accordance with the modified recipe. Effect of the Invention

[0011] According to a representative embodiment of the present invention, a technique is provided that can shorten the time required to obtain appropriate environmental parameters in a cell culture experiment. [Brief description of the drawings]

[0012] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a cell culture experimental system according to a first embodiment. [Diagram 2] 1 is a diagram showing an example of the external appearance of a main part of a cell culture experimental system according to a first embodiment. [Diagram 3] FIG. 1 illustrates an example of the configuration of a computer. [Figure 4] FIG. 2 is a diagram illustrating an example of a configuration of data stored in a database device. [Diagram 5] FIG. 1 is a diagram (part 1) showing an example of a process flow in the cell culture experimental system according to the first embodiment. [Figure 6] FIG. 2 is a diagram (part 2) showing an example of a process flow in the cell culture experimental system according to the first embodiment. [Figure 7] FIG. 3 is a diagram (part 3) showing an example of a process flow in the cell culture experimental system according to the first embodiment. [Figure 8] FIG. 11 is a diagram showing an example of an operation of the robot device according to the operation data. [Figure 9] FIG. 1 shows a step of detaching adherent cells in a cell culture process. [Figure 10] FIG. 1 is a diagram showing how multiple devices operate according to a common clock signal. [Figure 11] FIG. 11 is a diagram showing an example of a plurality of video data that are a part of the progress data. [Figure 12] 3 is a diagram showing a force sensor which is an example of a sensor unit of the detection device; FIG. [Figure 13] FIG. 13 is a diagram showing a specific example of contact between objects. [Figure 14] FIG. 11 is a diagram showing an example of data on pressure applied to an object in each process, which is a part of the progress data. [Figure 15] FIG. 13 is a diagram showing an example of a portion of progress data. [Figure 16] FIG. 13 is a diagram showing an example of a bar graph showing the distribution of a likelihood function. [Figure 17] FIG. 13 is a diagram showing an example of a table of a likelihood function that represents the relationship between a prior probability distribution and likelihood. [Figure 18] FIG. 13 is a diagram showing an example of a bar graph of posterior probabilities. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0013] <Details of the study by the present inventors> Before describing the embodiments of the present invention, a specific example will be used to describe problems that arise when Bayesian experimental design is applied to cell culture.

[0014] A typical Bayesian experimental design method uses post-hoc results to conduct experiments. For example, suppose there is a newly developed cultured cell line X. To verify the effects of X, assume that the results are verified for 20 randomly selected samples out of a total of 40 samples anticipated in advance. These 20 samples are called the validation group. The remaining 20 samples are then filled with fake cells. Fake cells are cells that are not expected to have any effect. These 20 samples are called the efficiency group. As a result, 4 samples in the validation group developed cancer (16 samples were successful), and 16 samples in the efficiency group developed cancer (4 samples were successful).

[0015] If it can be determined from these results that cultured cell X is effective, a reasonable decision can be made with 50% efficiency and without testing all 40 samples. First, the posterior probability distribution is calculated using the following Bayes' theorem.

[0016]

number

[0017] Incidentally, probability is actually a continuous value, but for simplicity, we will take the value of p (the probability that when one of the samples develops cancer, that sample belongs to the validation group) as discrete values ​​in increments of 0.1, such as 0.1, 0.2, 0.3, ..., 0.9 (= we use a discrete probability distribution).

[0018] In addition, in Bayesian estimation, the prior probability distribution uses subjective probability (uniform distribution). Generally, Bayesian statistics is, simply put, a method of calculating the posterior probability distribution (Posterior) from the prior probability distribution (Prior) and likelihood (Likelihood). As more data is collected, the posterior probability distribution becomes more accurate. Once your data is large enough, the prior probability distribution becomes almost completely irrelevant.

[0019] In Bayesian statistics, it is known that once enough data is collected, the proportion of the prior probability distribution in the calculation will eventually become so insignificant that it can be ignored.

[0020] In the first stage, we assume that we have no idea how effective cultured cell X is. Therefore, we assume that the nine models with p=0.1 to p=0.9 are equally likely, and the prior probabilities are uniformly set at 0.11 each (0.12 for p=0.5 to make the sum 1).

[0021] f(0.1)=0.11 (*The probability that p=0.1 is 0.11. The same applies below.) f(0.2)=0.11 f(0.3)=0.11 f(0.4)=0.11 f(0.5)=0.12 f(0.6)=0.11 f(0.7)=0.11 f(0.8)=0.11 f(0.9)=0.11

[0022] This probability distribution indicates that all prior probabilities are the same, that is, p=0.1 to p=0.9 are all equally likely, a uniform distribution. (To be precise, only p=0.5 is set to 0.12 in order to make the sum 1.)

[0023] Next, calculate the likelihood function. For example, the likelihood when the success rate is 0.5 is the same as the conditional probability that the number of successes will be 4 when the trial is performed 20 times, and can be calculated as follows:

[0024]

number

[0025] If we perform the same calculation for p values ​​from 0.1 to 0.9, we can obtain the respective likelihoods as follows:

[0026] p= 0.1 : 0.08977882814987155 p= 0.2 : 0.21819940194609996 p= 0.3 : 0.13042097437387037 p= 0.4 : 0.03499079040415815 p= 0.5 : 0.004620552062988271 p= 0.6 : 0.0002696861504765946 p= 0.7 : 5.007558331512445e-06 p= 0.8 : 1.3005697843199945e-08 p= 0.9 : 3.1788044999999754e-13

[0027] Fig. 16 is a diagram showing an example of a distribution of likelihood functions expressed as a bar graph. When the above-mentioned data are put together into a graph, the distribution of likelihood functions as shown in Fig. 16 is obtained.

[0028] The normalization constant is a constant for adjusting the sum of the probabilities of the posterior probability distribution to be calculated to 1. This is the sum of the corresponding prior probability distributions and likelihood functions calculated so far multiplied together.

[0029] Fig. 17 is a diagram showing an example of a likelihood function that represents the relationship between the prior probability distribution and the likelihood in a table. First, by summarizing the likelihood function that represents the relationship between the prior probability distribution and the likelihood in a table, the table shown in Fig. 17 is obtained.

[0030] The normalization constant is calculated by multiplying these values ​​one by one for each column and adding them together, so 0.11 x 0.0898 + 0.11 x 0.2182 + 0.11 x 0.1304 + 0.11 x 0.035 + 0.12 x 0.0046 + 0.11 x 0.0003 + 0.11 x 0.00 + 0.11 x 0.00 ≒ 0.053

[0031] From the above, we can use Bayes' theorem to find the posterior probability distribution. For example, to find the posterior probability when p=0.5, we get the following:

[0032]

number

[0033] This is the posterior probability of the p=0.5 model. This shows that the probability that the cancer incidence rate is 0.5 under the condition that the number of cancer cases is 4 out of 20 trials is only 1%.

[0034] The remaining eight models, ranging from p=0.1 to p=0.9, are calculated in the same manner as follows:

[0035] P(k=4| n=20, p= 0.1 ) : 0.1875450876140688 P(k=4| n=20, p= 0.2 ) : 0.45581154041134897 P(k=4| n=20, p= 0.3 ) : 0.27244522533562093 P(k=4| n=20, p= 0.4 ) : 0.07309463697920575 P(k=4| n=20, p= 0.5 ) : 0.010529656158194935 P(k=4| n=20, p= 0.6 ) : 0.0005633657039385877 P(k=4| n=20, p= 0.7 ) : 1.0460628472988208e-05 P(k=4| n=20, p= 0.8 ) : 2.716848495074202e-08 P(k=4| n=20, p= 0.9 ) : 6.640420472689636e-13

[0036] Fig. 18 is a diagram showing an example of a bar graph of the posterior probabilities. When the above-mentioned posterior probabilities are plotted on a bar graph, the graph shown in Fig. 18 is obtained.

[0037] If we look at the graph of the posterior probability distribution, we can see that there is an almost 100% probability that p<0.5 (probability of cancer development is less than 50%) (in fact, from the table in Figure 18, we can calculate this as 0.188+0.456+0.272+0.0731=0.989). In other words, there is a 98.9% possibility that cultured cell X is effective.

[0038] Among these probabilities, the probability of p=0.2 is the highest at 0.456. This shows that the probability that the cancerous cells are samples from the validation group (0.2) is 1 / 4 of the probability that they are samples from the efficiency group (0.8) (i.e., the application of cultured cell X is most likely to reduce the cancer rate to 1 / 4).

[0039] The above is an example of a commonly used Bayesian experimental design, in which it is possible to derive reasonable results even if the number of samples was reduced by 50% (i.e., with half the effort).

[0040] However, a problem with the culture environment to which the present invention is applied is that it takes a long time (e.g., four months) from the start of culture until the result is determined as normal cells (or cancerous cells). For this reason, it takes four months to obtain accurate results and derive an appropriate recipe, i.e., an intermediate environmental parameter set, through learning, and in principle it takes another four months before the next result is obtained using the intermediate environmental parameter set derived through learning. This is a factor that significantly reduces research efficiency.

[0041] In addition, since the Bayesian experimental design requires setting all probability distributions at once, it is necessary to conduct a huge number of experiments at once and obtain a huge number of results. However, in reality, even if the search period is effectively shortened by conducting a huge number of experiments at once, each experiment must be started sequentially according to the priority of the experiment, which means that the results must be compiled in order, which is an issue.

[0042] In view of the above circumstances, the present inventors have conducted intensive research and have come up with the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings.

[0043] In the drawings, the same elements are generally given the same reference numerals, and repeated explanations are omitted. When there are a plurality of identical or similar components, different suffixes may be added to the same reference numerals for explanation. In the drawings, the representation of each component may not represent the actual position, size, shape, range, etc., in order to facilitate understanding of the invention, and the present invention is not necessarily limited to the position, size, shape, range, etc., disclosed in the drawings. Representations such as identification information, identifiers, IDs, names, numbers, etc. for various data and information are interchangeable.

[0044] The functional blocks, circuits, computers, processing units, etc. that constitute a device or system may be realized by electronic circuits combining electronic components, but they may also be realized by an information processing device such as a processor or a computer including a processor executing a specified program.

[0045] The processor is composed of semiconductor devices such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), and an MCU (Micro Controller Unit). The processor is composed of devices and circuits capable of performing predetermined calculations. The processing is not limited to software program processing, and can also be performed by dedicated circuits. The dedicated circuits can be FPGAs (Field Programmable Gate Arrays), ASICs (Application Specific Integrated Circuits), etc.

[0046] The program may be installed as data in advance on the target computer, or may be distributed as data from a program source to the target computer and then installed. The program source may be a program distribution server on a communication network, or may be a non-transitory computer-readable storage medium. The program may be composed of multiple program modules. The computer system may be composed of multiple devices.

[0047] (Embodiment 1) <Cell culture experiment system configuration> Fig. 1 is a diagram showing an example of the configuration of a cell culture experimental system according to embodiment 1. As shown in Fig. 1, the cell culture experimental system 10 according to embodiment 1 includes equipment placed in an area SC1 for aseptic operations etc. that is assumed to be grade A, equipment placed in an area SC2 for aseptic operations etc. that is assumed to be grade B / C, equipment placed in a general control area SC3, and equipment placed in other areas SC4.

[0048] The sterile operation area SC1 is provided with a robot device 300, a detection device 400, and cell culture equipment 600. The sterile operation area SC2 is provided with a control device 100 and a terminal device 201. The general management area SC3 is provided with a terminal device 200. The other area SC4 is provided with a recipe judgment device 550 and a database device 500.

[0049] The equipment installed in the sterile operation area SC1 and the equipment installed in the sterile operation area SC2 and the general control area SC3 are connected to each other so that they can communicate with each other via a local bus LB. Also, the equipment installed in the sterile operation area SC2 and the equipment installed in the other area SC4 are connected to each other so that they can communicate with each other via a cloud network bus CB. Note that the connection between the equipment via each of the above buses is merely an example, and is not limited to the above connection method.

[0050] The control device 100 has an operation control unit 101 and a detection control unit 102. The operation control unit 101 transmits a control signal to the robot device 300 so that the robot device 300 performs an operation related to a cell culture experiment. The detection control unit 102 transmits a control signal to the detection device 400 so that the detection device 400 detects a predetermined physical quantity or data, and acquires detection data from the detection device 400.

[0051] The terminal device 200 and the terminal device 201 have an input unit and an output unit. The terminal device 200 and the terminal device 201 accept input settings and operations from a user, such as a researcher, through the input unit, and transmit control signals or data corresponding to the input settings and operations to the control device 100 or the detection device 400. The terminal device 200 and the terminal device 201 also obtain output signals or data from the control device 100 or the detection device 400, and output them to the user through the output unit. Note that the terminal device 200 and the terminal device 201 both allow input settings and operations related to the operation control of the robot device 300 by the user. However, in general, the user uses the terminal device 201 to perform input settings and operations related to the operation control of the robot device 300. The terminal device 200 may be, for example, a personal computer, a tablet terminal, a mobile information terminal, or the like.

[0052] The robot device 300 has various mechanisms, motors or actuators connected to the various mechanisms, and operates these mechanisms based on the received control signals to operate various steps related to the cell culture experiment. The robot device 300 also exchanges information with the cell culture equipment 600 and delivers samples of cells to be cultured.

[0053] The main steps in a cell culture experiment are, for example, as follows:

[0054] First, there is a process called "medium exchange." Cells use the nutrients they need from the culture medium and metabolize those nutrients. For this reason, the medium, which has a low nutrient content and high metabolic products, is discarded and replaced with new medium. This task (process) is called "medium exchange."

[0055] Secondly, there is a process called "cell passaging." This requires the collection of a portion of the cultured cells and transferring them to a new culture vessel. This process is also called subculture. Cells divide repeatedly during culture, increasing their number, until they eventually fill up the culture vessel or the nutrients in the medium are depleted.

[0056] Thirdly, there is a process called "cell seeding." Based on the measured cell count / cell concentration, an appropriate amount of "culture medium" is added to dilute the cell suspension, and a specified amount of the cell suspension is transferred to a new culture vessel. This can also be described as the process of adjusting the cell concentration to the desired concentration and seeding the suspension evenly into the culture vessel. A "cell suspension" is a suspension of cultured cells (or microorganisms) in a liquid medium.

[0057] Further, more specific work contents in various steps of a cell culture experiment, that is, operations performed by the robot device 300, are as follows.

[0058] The first is the operation called "pipetting." It refers to sucking up and discharging a liquid (cell suspension) with a pipette. In cell culture, repeatedly sucking up and discharging a cell suspension with a pipette can also serve to loosen the cells in the cell suspension.

[0059] The second step is the "spreading" step, which is the process of spreading the cell suspension evenly over the bottom surface of the flask. The third is the operation of "dispensing." This refers to the process of accurately transferring a specified amount of liquid, such as culture medium, drug solution, or cell suspension, to a plate or chip using a pipette.

[0060] The detection device 400 detects information related to the operation of the robot device 300. The detection device 400 includes an imaging unit 401 and a sensor unit 402.

[0061] The imaging unit 401 is provided in a laboratory and captures images of operations performed by the robotic device 300, for example, operations corresponding to each step constituting a cell culture experiment of the robotic device 300. The imaging unit 401 is, for example, a digital video camera, and outputs video data obtained by capturing images.

[0062] The sensor unit 402 has one or more force sensors. The one or more force sensors are provided in various mechanisms of the robot device 300, detect forces, pressures, distortion forces, twisting forces, etc. applied to the various mechanisms as the robot device 300 operates, and output data corresponding to the detected physical quantities. The sensor unit 402 also has one or more environmental sensors. The one or more environmental sensors are provided in a laboratory, detect environmental temperature, environmental humidity, air pressure, atmospheric composition, etc. in the laboratory, and output data corresponding to the detected physical quantities.

[0063] The detection control unit 102 controls the time or period during which the imaging unit 401 captures images, and cooperates with the operation control unit 101 to synchronize the timing of operations or processes, if necessary.

[0064] The cell culture equipment 600 includes a culture unit 601 , a measurement unit 602 , and a chemical solution installation unit 603 .

[0065] The culture unit 601 includes an incubator and the like, and cultures cells at a constant temperature and humidity. The measurement unit 602 measures physical quantities that indicate the culture state of all or part of the cultured cells. The chemical solution installation unit 603 stores culture media as nutrients for culturing cells, chemical solutions used for measurement, or consumables for adding chemical solutions, instruments for aspirating and discharging liquids such as culture solution or chemical solutions, and their consumables.

[0066] The database device 500 has a data storage area such as a cloud system that stores various data and information sent from the terminal devices 200, 201, the detection device 400, the recipe judgment device 550, the cell culture equipment 600, etc., and passed through the control device 100. The data stored in the database device 500 includes, for example, video data obtained by the detection device 400, environmental data, judgment result data obtained by the recipe judgment device 550, history data of judgment recipes judged in the past, etc. The data acquired by each of the above devices during the experiment and stored in the database device 500 is called intermediate data.

[0067] The recipe judgment device 550 sets a recipe to be applied to each of a plurality of samples of cells to be cultured. In addition, in order to make the experiment more efficient, the recipe judgment device 550 stores the priorities of verification for a plurality of types of environmental parameters constituting the recipe. The top N environmental parameters in terms of priority are called a judgment recipe. The recipe judgment device 550 refers to intermediate data from the database device 500 in order to correct and update the judgment recipe according to a predetermined algorithm.

[0068] The cell culture experiment is carried out through the operation of the robot device 300. The robot device 300 carries out the experiment in cooperation with other devices or units. For example, the robot device 300 temporarily delivers the workpiece of cultured cells to the culture unit 601 and retrieves it, or delivers it to the measurement unit 602 for measurement and then retrieves it and starts the operation, or takes in a chemical solution from the chemical solution installation unit 603 and uses it on the cultured cells.

[0069] The priority order of experiments to be performed by the robot device 300, predetermined processes, etc. are instructed by the operation control unit 101. Operations to be performed by the robot device 300 through the operation control unit 101 are determined in advance by the recipe judgment unit 550 based on recipes set for each sample. The recipe judgment unit 550 selects verification parameters, which are environmental parameters to be verified. Alternatively, it assigns priorities to sampling and instructs the operation control unit 101 to perform experiments according to the priorities.

[0070] The recipe judgment device 550 corrects the judgment recipe from trend analysis of the state of the cultured cells based on the intermediate data stored in the database device 500. The recipe judgment device 550 corrects the past judgment recipe using the result index stored in the database device 500. When the artificial intelligence in the recipe judgment device 550 finds a causal relationship between the environmental parameters and the expected culture result that is different from the conventional one in the intermediate data, the recipe judgment device 550 improves the weight judgment of the trend analysis of the sample cell culture based on the intermediate data, i.e., the standard for judging the trend in the trend analysis.

[0071] Here, the main functions of each device constituting the cell culture experimental system 10 according to the first embodiment can be summarized as follows.

[0072] The control device 100 sets a recipe to be applied to each of a plurality of cell samples to be cultured. The control device 100 controls the operation of the robot device 300 so that the robot device 300 performs a culture experiment on a plurality of samples according to the set recipe. The database device 500 stores interim data for each sample in chronological order during one culture experiment in which the culture results of the plurality of samples are finalized.

[0073] The recipe judgment device 550 analyzes the tendency of culturing each sample based on the intermediate data for each sample stored in the database device 500. For each sample, the recipe judgment device 550 calculates a posterior probability representing the degree of possibility that the parameter values ​​of multiple environmental parameters constituting the set recipe will cause future successful culturing of the sample based on the analysis result of the tendency of culturing the sample and the difference between the time-series intermediate data of the sample. The recipe judgment device 550 determines one or multiple environmental parameters with a relatively high calculated posterior probability as verification parameters. The recipe judgment device 550 modifies the recipe for each sample by changing the parameter values ​​of the determined verification parameters.

[0074] The control device 100 controls the operation of the robotic device 300 so that the robotic device 300 continues to perform multiple culture experiments according to the modified recipe.

[0075] FIG. 2 is a diagram showing an example of the appearance of the main parts of the cell culture experimental system according to the first embodiment. As shown in FIG. 2, the system includes a control device 100, a terminal device 201, a robot device 300, and a detection device 400. A table 620 is also provided, and a plurality of tools 610 to be processed and operated by the robot device 300 are placed on the table 620. The tools 610 include a test tube 611, a pipette 612, a container 613, a well plate 614, a flask 615, and the like. The test tube 611, the pipette 612, and the container 613 included in the tools 610 are each operated by the robot device 300. The robot device 300, the plurality of tools 610, and the like are imaged by the imaging unit 401. The environmental temperature, environmental humidity, air pressure, and atmospheric composition in the laboratory are detected by an environmental sensor included in the sensor unit 402. Furthermore, pressure, twisting force, distortion force, and the like generated in various mechanisms constituting the robot device 300 are detected by a force sensor included in the sensor unit 402.

[0076] The robot device 300 has a base placed on the floor. The robot device 300 also includes a rotatable joint connected to the base and an arm connected to the joint. A joint and an arm are further connected to the tip of the arm. A gripper for gripping the instrument 610 is connected to the tip of the arm. The robot device 300 moves and operates the instrument 610 by using the joint, arm, gripper, and the like. An image captured by the imaging unit 401 is displayed on an output unit of the terminal device 201 via the control device 100, for example. The robot device 300, the table 620, the instrument 610, and the like are placed in a sterile operation area SC1. By placing the instrument 610, and the like in the sterile operation area SC1, it is possible to prevent foreign matter, and the like from being mixed into the sample, and the like. Other devices, such as a device for transporting the instrument 610, and the like, may be placed in the sterile operation area. In this example, the terminal device 201 is placed in a sterile operation area SC2 different from the sterile operation area SC1, and can be operated by a user. Note that the area in which the terminal device 201 is placed may be any other area having a lower cleanliness grade than the sterile operation area SC1, and is not limited to this example.

[0077] The control device 100, the database device 500, and the recipe judgment device 550 can be realized using a dedicated or general-purpose computer such as a PC (Personal Computer) or a workstation (WS, Work Station), or an electronic device equipped with a computer. The terminal device 201 can be realized using a dedicated or general-purpose computer such as a PC, a smartphone, a mobile phone, a tablet terminal, or a PDA (Personal Digital Assistant), or an electronic device equipped with a computer.

[0078] Fig. 3 is a diagram showing an example of the configuration of a computer. As shown in Fig. 3, the computer 90 has a processor 91, a memory 92, a storage 93, an input unit 94, an output unit 95, a communication control unit 96, and a communication bus 97. The processor 91, the memory 92, the storage 93, the input unit 94, the output unit 95, and the communication control unit 96 are connected to each other via the communication bus 97 so as to be able to transmit and receive signals. A predetermined program PG is stored in the storage 93. The computer 90 functions as, for example, a control device 100, a database device 500, or a recipe determination device 550 by the processor 91 reading out the program PG, expanding it in the memory 92, and executing it.

[0079] Fig. 4 is a diagram showing an example of the configuration of data stored in the database device. As shown in Fig. 4, the database device 500 stores, for each cell sample that is the subject of a culture experiment, a sample number (No.) given to the sample, progress data related to the sample, an experiment result index, and the like, in association with each other.

[0080] <Processing flow in cell culture experimental system> Here, an example of the process flow in the cell culture experimental system 10 according to the first embodiment will be described.

[0081] 5 to 7 are diagrams showing an example of a process flow in the cell culture experimental system according to the first embodiment.

[0082] As shown in FIG. 5, in step S101, the initial setting of the determination recipe is performed. Specifically, the user inputs information that specifies the initial setting of the recipe to be set for a plurality of cell samples (hereinafter also simply referred to as samples) from the terminal device 201. The plurality of samples are divided into a group called a "verification group" and a group called an "efficiency group". The terminal device 201 transmits the input information of the initial setting to the recipe determination device 550. Based on the received information of the initial setting, the recipe determination device 550 stores information of the recipe of each sample belonging to the verification group and information of the recipe of each sample belonging to the efficiency group in a storage unit of the recipe determination device 550.

[0083] Next, in step S102, the likelihood is calculated. This "likelihood" corresponds to the "likelihood" used in Bayes' theorem. In step S102, specifically, the recipe judgment device 550 accesses the database device 500 and judges whether there is intermediate data of a plurality of samples. If it is judged that there is no intermediate data, the recipe judgment device 550 uses an artificial intelligence (AI) that has been trained based on the results of cell culture experiments up to now to obtain the likelihood for the currently set recipe as an estimated value. On the other hand, if it is judged that there is intermediate data, the recipe judgment device 550 reads the intermediate data of a plurality of samples from the database device 500, substitutes the read intermediate data into a predetermined calculation formula, and calculates the likelihood for each sample.

[0084] Next, in step S103, a posterior probability is calculated. This "posterior probability" corresponds to the "posterior probability" used in Bayes' theorem, and here indicates the probability that the future culture will be successful if the sample is cultured according to the recipe. More strictly, the posterior probability is the success rate of cell culture for each environmental parameter to be verified (e.g., score: 0% to 100%). In step S103, specifically, the recipe determination device 550 uses the above-mentioned artificial intelligence to calculate the posterior probability for each environmental parameter in the recipe for each sample, based on the prior probability preset according to the recipe for each of the multiple samples and the calculated likelihood, according to Bayes' theorem.

[0085] Next, in step S104, the n-th judgment recipe is modified. As described above, this "judgment recipe" refers to the recipe to be judged that is set for each sample. The recipe is repeatedly rewritten and modified multiple times based on the progress data obtained during the culture experiment according to the recipe. Therefore, the recipe to be judged at the present time is called the judgment recipe here.

[0086] Specifically, in step S104, the recipe judgment device 550 uses the above-mentioned artificial intelligence to rewrite the judgment recipe for each sample in the verification group and the efficiency improvement group using Bayes' theorem based on the posterior probability calculated for that sample.

[0087] The judgment recipe is composed of a list of multiple types of environmental parameters to be verified and a priority order for each environmental parameter. The priority order is determined from the results of trend analysis of cell culture based on intermediate data. Trend analysis of intermediate data means analyzing the trends of intermediate cell culture based on intermediate data, or knowing the status of cell growth (proliferation), such as acceleration, stagnation, and cancer. Cell culture often takes a long time. During the culture, growth may gradually stagnate, cells may suddenly become cancerous at a certain point, or in some cases, the stagnant growth may begin to accelerate. Trend analysis means analyzing the trends of such intermediate cell culture.

[0088] Here, the recipe judgment device 550 uses artificial intelligence to analyze the intermediate data, calculates the degree to which each environmental parameter is likely to be related to the success or failure of cell culture, i.e., a priority order, and assigns the priority order to each environmental parameter. Then, the environmental parameters with the top N priorities are set as verification parameters that are parameters to be verified, and the verification parameters are assigned parameter values ​​and distributed to the recipes of multiple samples. In other words, the recipe judgment device 550 extracts verification parameters from the analysis results of the intermediate data, and assigns parameter values ​​to the environmental parameters corresponding to the extracted verification parameters among the environmental parameters of the recipes of multiple samples.

[0089] In other words, instead of thoroughly verifying all patterns in the combination of values ​​of many environmental parameters, the system extracts patterns that are determined to have high priority based on recipe judgment, and verifies the recipe of that pattern. In other words, the contents of the culture process for each sample are modified. The above priority is a posteriori probability and is derived by artificial intelligence.

[0090] The artificial intelligence used here has been trained or continues to be trained to prioritize verification parameters so that samples set with a combination of environmental parameter types and parameter values ​​that are thought to be highly likely to contribute to cell culture success will have a higher success rate, and conversely, samples set with a combination of environmental parameter types and parameter values ​​that are thought to be highly likely to contribute to cell culture failure will have a higher failure rate (lower success rate). In other words, the artificial intelligence is capable of making rational decisions to reduce the number of verification parameters, for example, by prioritizing "only the top 20% of verification parameters need to be verified."

[0091] The judgment recipe is rewritten, i.e., modified, so that the posterior probability is higher for samples in the validation group, and lower for samples in the efficiency group. The "nth" in the nth judgment recipe starts at n=1 and increases with each rewrite, to n=2, n=3, ...

[0092] Next, in step S105, it is determined whether or not there is a change in the cell state of the samples belonging to the verification group. That is, it is determined whether or not to reset the configuration of samples in the verification group and the efficiency improvement group. Specifically, the recipe determination device 550 determines whether or not to reset the configuration of samples belonging to the verification group and the efficiency improvement group so that the verification group becomes a group with a higher priority, based on whether or not there is a change in the verification group of a predetermined parameter number of samples.

[0093] For example, the recipe judgment device 550 judges whether or not there is a change in the cell state of a sample belonging to the verification group based on information included in the intermediate data, such as the number (density) of cells, the proliferation rate of cells, and whether or not the cells have become cancerous. If it is judged that there is a change in the cell state (S105: Yes), the processing step proceeds to step S106 to reset the configuration of the verification group and the efficient group. On the other hand, if it is judged that there is no change in the cell state (S105: No), the processing step proceeds to step S107 to maintain the configuration of the samples in the verification group and the efficient group.

[0094] In step S106, the configuration of samples in the verification group and the efficient group is reset. Specifically, the recipe judgment device 550 resets the configuration of samples belonging to the verification group and the efficient group based on the change in the state of the cells using artificial intelligence. More specifically, the artificial intelligence resets the configuration of samples in the verification group and the efficient group so that, as described above, a group of samples in which a combination of a type of environmental parameter that is thought to be highly likely to contribute to the success of cell culture and a parameter value thereof is set has a higher success rate of culture, and conversely, a group of samples in which a combination of a type of environmental parameter that is thought to be highly likely to contribute to the failure of cell culture and a parameter value thereof is set has a lower success rate of culture (higher failure rate). After that, the processing step proceeds to step S108.

[0095] In step S107, the configuration of samples in the verification group and the efficiency improvement group is maintained. Specifically, the recipe judgment device 550 maintains the current configuration of samples belonging to the verification group and the efficiency improvement group without changing them. After that, the processing step proceeds to step S108.

[0096] In step S108, an experiment is started. Specifically, the operation control unit 101 starts a process of transmitting a control signal to the robot device 300 so that the culture experiment is started for each sample belonging to the verification group and the efficiency improvement group in the order of the set priority, and the culture experiment is performed according to the recipe set for each sample. In addition, the operation control unit 101 transmits a control signal to the devices of the cell culture device 600 as necessary, so that the cell culture device 600 performs preparations, condition settings, etc. required for the experiment. In addition, the detection control unit 102 transmits a control signal to the detection device 400 as necessary, so that the detection device 400 performs imaging by the imaging unit 401 or data acquisition by the sensor unit 402.

[0097] In step S109, it is determined whether or not the final result of the culture experiment has been obtained. Specifically, the control device 100 accesses the database device 500, determines whether information related to the final result of the culture experiment currently being performed is stored, and determines whether or not the final result of the culture experiment currently being performed has been obtained based on the determination result. If it is determined that the final result has been obtained (S109: Yes), the processing step proceeds to step S114 so that the culture result is checked. On the other hand, if it is determined that the final result has not been obtained (S109: No), the processing step proceeds to step S110 so that intermediate data is stored in the database device 500.

[0098] In step S110, intermediate data during a predetermined operation process period of the robot device 300 is acquired. Specifically, the detection device 400 acquires video data of the operation of the robot device 300 for an operation process currently being performed among a plurality of predetermined operation processes of the robot device 300 (S110-1), and acquires environmental data such as temperature, humidity, and air pressure in the laboratory (S110-k). In addition, the detection device 400 acquires operation data, which is control data that specifies the operation of the robot device 300 in each operation process, from the recipe judgment device 550 or the control device 100.

[0099] In step S111, it is determined whether the acquired intermediate data has a characteristic in light of a criterion. Specifically, the recipe determination device 550 stores criterion information for each type of intermediate data, and determines whether the acquired intermediate data has a characteristic by comparing it with the criterion. Note that the determination here may be a threshold determination of an index value obtained based on the intermediate data, or may be a determination based on an analysis result of the intermediate data by artificial intelligence.

[0100] For example, the recipe judgment device 550 uses artificial intelligence or a user's evaluation or input to determine whether or not there is a characteristic operation different from an expected operation in video data in which the operation of the robot device 300 is recorded (S111-1). Also, for example, the recipe judgment device 550 uses artificial intelligence or a user's evaluation or input to determine whether or not there is a characteristic in the environmental data, such as temperature, humidity, air pressure, etc. being different from an expected reference value by a predetermined level or more (S111-k). Also, for example, the recipe judgment device 550 uses artificial intelligence or a user's evaluation or input to determine whether or not there is a characteristic control in the operation data of the robot device 300.

[0101] The process proceeds to step S112 for processing the environmental parameters determined to have characteristics in step S111. On the other hand, the process proceeds to step S113 for processing the environmental parameters determined to have no characteristics in step S111.

[0102] In step S112, a marking indicating a characteristic is added to the intermediate data. Specifically, the recipe judgment device 550 adds a marking indicating a portion determined to have a characteristic in the intermediate data. For example, the recipe judgment device 550 adds a marking to the moving image data, which is associated with the start of a time period during which an operation determined to have a characteristic is performed in the moving image data (S112-1). Also, for example, the recipe judgment device 550 adds a marking to the environmental data, which is associated with the start of a time period during which a change determined to have a characteristic occurs in the environmental data (S112-k). After the addition of the marking is completed, the process proceeds to step S113.

[0103] In step S113, intermediate data is stored for each sample. Specifically, the control device 100 stores intermediate data for each sample in the culture experiment in a storage area of ​​the database device 500. A folder is prepared for each sample number in the database device 500, and intermediate data for each sample is stored in the folder for that sample number. That is, intermediate data corresponding to each operation step of the robot device 300 in the culture experiment for each sample is accumulated in a folder prepared for each sample. When storage of intermediate data is completed, the process returns to step S102.

[0104] In step S114, the final culture results are checked. Specifically, the control device 100 outputs the final culture results of each sample in the validation group and the efficiency improvement group to the user by displaying them on the screen of the display unit of the terminal device 201. A user such as a researcher refers to the culture results and inputs a success index of the culture experiment for each sample. When the input is completed, the processing step proceeds to step S115.

[0105] In step S115, it is determined whether or not the success index is within a preset range. Specifically, the recipe determination device 550 determines, for each sample, whether or not the value of the success index is within a preset range of m to n.

[0106] In this judgment, for a sample whose success index is judged to be within the set range (S115: Yes), the recipe judgment device 550 sets the result that the success index of the sample is within the set range as a result index, and stores the result index in the folder of the target sample in the database device 500 (S116).

[0107] On the other hand, for a sample whose success index is not within the set range in this judgment, that is, whose success index is judged to be outside the set range (S115: No), the recipe judgment device 550 determines the result that the success index of the sample is outside the set range as the result index. Also, a user such as a researcher checks the cause of the result and inputs information indicating the cause through the terminal device 201 (S117). For example, the user extracts differences that have brought about an extremely good or bad result from the intermediate data, and adds the extracted results to the result index by operating the terminal device 201, and stores them in the database device 500. Also, for example, the recipe judgment device 550 uses artificial intelligence to investigate the causal relationship between the cause and the intermediate data for the sample, adds the investigation result to the result index, and stores the result index in the folder of the target sample in the database device 500 (S118).

[0108] When the processing for each sample in steps S115 to S118 is completed, the processing proceeds to step S119.

[0109] In step S119, it is determined whether or not to end the experiment. Specifically, the control device 100 determines whether or not to end the culture experiment based on information input by the user through the terminal device 201, or based on information representing a preset experiment plan. If it is determined that the culture experiment is to be ended (S119: Yes), the processing related to the culture experiment ends. On the other hand, if it is determined that the culture experiment is not to be ended, that is, to be continued (S119: No), the processing step returns to step S102, and the processing related to the culture experiment continues.

[0110] 5 to 7, the intermediate data and the evaluation results for each operation step of the robot device 300 and for each sample are stored in the database device 500. Then, based on the accumulated intermediate data, the recipes of each sample in the verification group and the efficiency group, i.e., the parameter sets of the intermediate environmental parameters, are sequentially modified. As a result, the verification group will be filled with samples with recipes having a high probability of successful cultivation, and the efficiency group will be filled with samples with recipes having a low probability of successful cultivation.

[0111] The recipes of the samples in the validation group converged in this way reveal the types of environmental parameters and their conditions that are likely to lead to successful cultivation, while the recipes of the samples in the efficiency group converged in this way reveal the types of environmental parameters and their conditions that are likely to lead to failure in cultivation, or the types of environmental parameters that are likely to have no effect on the success or failure of cultivation.

[0112] The definition of successful cell culture varies depending on the user of the system, and there is no specific condition. Successful cell culture can be defined, for example, as the normality and number of cells after the completion of the culture process satisfying a preset condition. It can also be defined as the normality and number of cells satisfying a preset condition after the completion of the culture process and the freezing process being successful. The user of the system may decide the definition of successful culture and intuitively add the success index (score) for each sample as accompanying data of the result index.

[0113] One of the most distinctive features of the first embodiment is that video data, operation data, data detected by sensors, and the like related to the operation of the robot device 300 during an experiment are stored as intermediate data. Research to date has revealed that the success or failure of cell culture is affected by operations such as how a container containing cells is handled, how a chemical solution or cell liquid is aspirated or discharged with a pipette, and what kind of impact is given to the cells. Therefore, storing data related to the operation of the robot device 300 related to these operations as intermediate data is extremely important in searching for an appropriate recipe for successful culture, i.e., the types of environmental parameters and their conditions.

[0114] That is, the intermediate data may be, for example, information related to the operation of the robot device 300 that has been corrected for each sample as intended by the user. The information related to the operation of the robot device 300 may be, for example, information on the trajectory of the movement of the tool being handled, the speed of the movement of the tool, the acceleration of the movement of the tool, the posture of the tool, the pressure applied by the tool to the target object, the twisting force applied by the tool to the target object, etc. This information is different from uniform data that has been determined in advance by teaching. Specific examples of intermediate data will be described below.

[0115] <Example of progress data 1> Fig. 8 is a diagram showing an example of the operation of the robot device related to the operation data. As an example of the operation data stored as the intermediate data, data related to the operation of the robot device 300 when a liquid 651, which is a drug solution or a cell liquid in a petri dish 650, is sucked once with a pipette 652 and then discharged, as shown in Fig. 8, is considered. The operation data includes data representing operations corresponding to each condition, such as a discharge start position P1, a trajectory RT of the pipette during discharge, a discharge end position P2, a natural separation of cell aggregates by applying the pipette 652 to the wall of the petri dish 650, a quiet mixing by the liquid 651 spilling from right to left (F8a in Fig. 8), and a natural rotation of the fluid by the liquid 651 spilling from left to right (F8b in Fig. 8).

[0116] <Example of progress data 2> The control device 100 operates the robot device 300 based on the created operation data, i.e., the scenario. The detection device 400 monitors the operation of the robot device 300 and outputs it to the user from the terminal device 201. When the robot device 300 is operating based on the scenario, the control device 100 accepts an input of a correction of the operation by the user to the terminal device 201 and corrects the scenario.

[0117] Fig. 9 is a diagram showing the detachment process of adherent cells in the cell culture process. In the detachment process of adherent cells as shown in Fig. 9, most of the cells can be properly collected by scraping with a scraping tool, but some cells are damaged and killed due to impact during scraping.

[0118] For example, suppose that the detector 400 detects a scraping action on a cell in a certain time period in video data. The speed of the scraping action is about 10 cm / sec when performed by human hands. If the video of the scraping action is important as intermediate data, it will be important to capture the event from when the scraping action starts to have a physical effect on the cell in the vicinity of the cell until it comes into contact with the cell and some event occurs, that is, a distance section roughly equal to or larger than the size of the cell, i.e., about 100 μm.

[0119] In the above example, simple calculations show that the time required for the robot device 300 to scrape off a section of about 100 μm is at most 1 ms. Therefore, time consistency is required between multiple devices to ensure that a series of operations have been performed within a short period of 1 ms.

[0120] FIG. 10 is a diagram showing how a plurality of devices operate according to a common clock signal. In general, the control device 100, the robot device 300, the detection device 400, and the terminal devices 200 and 201 are controlled by a common clock signal output from a clock device 103 having an accuracy of the order of μs, as shown in FIG. 10. Therefore, it is possible to guarantee the mutual time identity between the devices as required in the above example. That is, it is possible to match the operations of each device for events performed within 1 ms, and it is possible to secure intermediate data such as "a series of operations from xx minutes xx seconds 500 milliseconds to xx minutes xx seconds 501 milliseconds." Note that the time error representing the accuracy of the common clock signal output from the clock device 103, for example, the error in the time interval of the rising edge, is preferably 10 μS (microseconds) or less.

[0121] Fig. 11 is a diagram showing an example of multiple video data that are part of the progress data. In the above example, for each sample, multiple video data are acquired as the progress data, for example, as shown in Fig. 11. The example in Fig. 11 shows how multiple video data are acquired as the progress data H11 for sample No. 1. Each piece of video data that constitutes the progress data H11 is data in which, for example, the progress data No., start time, end time, and video number are associated with each other.

[0122] If the time of each device were not consistent, for example, it would be impossible to determine at what time period the detected motion was caused by the operation of the robot device 300, and the interim data would be meaningless. In this way, it is possible to secure a series of interim data in which the devices are linked by utilizing the time consistency. Depending on the application in the research field, there may be cases where verification of more microscopic motions is required, and in this case, it goes without saying that a more accurate time consistency is required.

[0123] <Example of progress data 3> A specific example 3 of the intermediate data is an example in which measurement data of the pressure generated in the culture tool, obtained by a force sensor, is used as the intermediate data.

[0124] Fig. 12 is a diagram showing a force sensor, which is an example of a sensor unit of a detection device. For example, as shown in Fig. 12, the force sensor 402a has a configuration that utilizes a lever, and is a sensor that detects a pressure PA1 that an operating tool 402b held by a part 300a of the robot device applies to an object it comes into contact with by detecting a pressure PA2 that is generated by the principle of action and reaction. The force sensor 402a is configured by combining a plurality of sensors, called strain sensors, that convert pressure into an electric signal, and can quantitatively grasp pressure.

[0125] FIG. 13 is a diagram showing a specific example of contact of objects. The first example relates to a peeling operation process of adherent cells. More specifically, the first example relates to a peeling process of adherent cells on the bottom surface 661 of a petri dish, for example, as shown in FIG. 13, reference symbol F13a, in which a scraping tool 663 is moved while pressing the cells 662 cultured while adhering to the bottom surface 661 of the petri dish to peel the cells. It is important to operate the scraping tool while applying a predetermined pressure to the bottom surface 661 of the petri dish so as not to damage the cells 662 and to peel them sufficiently. Therefore, the degree of pressure PA3 applied to the bottom surface 661 of the petri dish, that is, the measured value of this pressure PA3, can be intermediate data.

[0126] The second example relates to a sample extraction operation process. More specifically, the second example relates to an operation process in which a sample 665 in a test tube 664 is extracted by pressing an instrument 666 against the inner wall of the test tube 664 and pulling it out, as shown in Fig. 13, reference symbol F13b. In this case, the degree of pressure PA4 applied to the inner wall surface of the test tube 664, i.e., the measured value of this pressure PA4, can be intermediate data.

[0127] The third example relates to a test tube cap opening and closing operation process. More specifically, the third example relates to a process in which gripping mechanisms 310, 311 of a robot device grip and open / close cap 668 in an operation of rotating cap 668 of a test tube 667, as shown in Fig. 13, reference symbol F13c. In this case, the degree of pressure PA5 applied to cap 668 when opening and closing cap 668 of test tube 667, i.e., the measured value of this pressure PA5, can be intermediate data.

[0128] FIG. 14 is a diagram showing an example of data of pressure applied to an object in each step, which is a part of the progress data. A force sensor can have multiple parameters, such as pressure in the axial direction or pressure in the torque direction. For each sample, data of detected pressures on the x-axis, y-axis, and z-axis in each step are acquired as progress data, for example, as shown in FIG. 14. The example of FIG. 14 shows a state in which multiple detected pressure data are acquired as progress data H14 for sample No. 1. The individual detected pressure data constituting the progress data H14 is data in which, for example, a progress data No., a detected pressure on the x-axis, a detected pressure on the y-axis, a detected pressure on the z-axis, and a case (step) are associated with each other. Examples of the case (step) can be, for example, peeling of adherent cells, taking out a specimen, opening a test tube lid, closing a test tube lid, and the like.

[0129] In this way, it is possible to secure, as intermediate data, what kind of force sense was used to perform the operation by the robot device 300 in each step of the culture experiment.

[0130] <Other examples of progress data> Potential intermediate data are of course not limited to the above, and include, for example, the following: the angle at which the pipette is held, the speed at which the pipette's flanger is pushed and pulled, the timing at which the flanger is pushed and pulled, the acceleration when the flanger is moved, the conditions for the operation of the tip attached to the end of the pipette from contacting the liquid to removing it, the speed at which the petri dish is moved, the inclination of the petri dish when it is moved, the opening and closing speed of the incubator door, etc. These can be intermediate data, but at the same time, they can also be considered environmental parameters that make up the recipe to be verified.

[0131] Fig. 15 is a diagram showing an example of a portion of the intermediate data. As shown in Fig. 15, as a portion of the intermediate data, for example, an intermediate data number, a timing of modification of the culture recipe, a modified culture recipe, a likelihood, and a posterior probability are stored in association with each other.

[0132] <Examples of Effects of the First Embodiment> As described above, according to the first embodiment, in a cell culture experiment in which the post-test results have not been obtained or it will take a long time for the post-test results to be known, the artificial intelligence that has learned the relationship between the environmental parameter settings and the culture results based on the results of many past experiments determines the verification priority of the environmental parameters based on the first judgment recipe. The first judgment recipe has intermediate data secured as supplementary information, and the first judgment recipe is corrected based on the intermediate data. The corrected first judgment recipe is then applied to the next similar judgment recipe. In this way, by utilizing recipes that are successively corrected and updated during the culture experiment, it becomes possible to estimate the success or failure of the culture, or the environmental parameters and their conditions related to the culture success, before the final result of the culture experiment is obtained.

[0133] Furthermore, according to the first embodiment, when a difference occurs in the cell culture state due to a change in the recipe, the difference in the intermediate data previously attached to that recipe is extracted, and the experimental result is predicted at the point when a difference appears in this intermediate data. This makes it possible to shorten the experimental period, eliminate wasteful experiments, and discover causal information collection.

[0134] Let us suppose that we use a cell culture experiment system that is performed by a robot without modifying a predetermined scenario, and search for optimal values ​​for some of the many environmental parameters that make up the cell culture recipe. The environmental parameters to be searched for are, for example, the drug concentration and drug addition time in process 1, the drug treatment time in process 2, the cell detachment amount, the cell detachment strength, the drug concentration and drug addition time in process 3, etc. The timing for changing the environmental parameters to be searched for is after the experiment is completed, and the environmental parameters to be searched for can be changed automatically. However, if there are many environmental parameters, it will take a long time, for example, four months, to complete all the experiments.

[0135] It would be fine if the number of environmental parameters to be explored was something that could be determined in advance by humans, but the overwhelming majority of them are not. Therefore, in such a system, it is necessary to repeat the process of varying all environmental parameters, conducting incubation experiments, feeding back the results, and conducting incubation experiments again, which takes a very long time. In other words, exploration is practically difficult.

[0136] On the other hand, in the cell culture experimental system according to the first embodiment, the intermediate data is analyzed, the degree (priority) of each environmental parameter's likelihood of being related to the success or failure of cell culture is calculated, and the degree is assigned to each parameter. The top N parameters are then set as verification parameters, and the values ​​of the verification parameters are distributed and set among multiple samples. In other words, the contents of the culture process for each sample are modified. The above-mentioned degree is a posteriori probability, and is derived by artificial intelligence.

[0137] If an environmental parameter is found that indicates an extreme value for the posterior probability (singular point: outside the range of 20% to 80%), it is possible that equipment has been lost or an accident has occurred during the experiment. In such cases, humans will intervene to identify the causal relationship and add the identified cause to the interim data.

[0138] (Embodiment 2) A cell culture experimental method according to an embodiment of the present invention will be described below.

[0139] The recipe judgment device sets a recipe to be applied to each of a plurality of samples of cells to be cultured. The control device controls the operation of the robot device so that the robot device performs a culture experiment of a plurality of samples according to the set recipe. The database device stores interim data for each sample in a time series during one culture experiment in which the culture results of the plurality of samples are determined. The recipe judgment device analyzes a trend in the culture of each sample based on the interim data for each sample stored in the database device, and calculates, for each sample, a posterior probability representing a degree of possibility that a parameter value of a plurality of environmental parameters constituting a set recipe will cause future success in the culture of the sample based on a difference between the analysis result of the trend in the culture of the sample and the chronological interim data of the sample. The recipe judgment device determines one or more environmental parameters with a relatively high calculated posterior probability as a verification parameter, and modifies the recipe for each sample by changing the parameter value of the determined verification parameter. The control device controls the operation of the robot device so that the robot device continues to perform a plurality of culture experiments according to the modified recipe.

[0140] This cell culture experimental method has the same effect as the cell culture experimental system of embodiment 1, i.e., it is possible to determine and implement the next recipe to be evaluated without waiting for the actual experimental results, thereby shortening the time required to obtain an appropriate set of environmental parameters.

[0141] (Embodiment 3) A program according to an embodiment of the present invention will be described below.

[0142] a recipe determination device that sets a recipe to be applied to each of a plurality of samples of cells to be cultured; a control device that controls the operation of the robotic device so that the robotic device performs a culture experiment of a plurality of samples according to the set recipe; and a program for causing one or a plurality of computers or processors to function as a database device in which interim data for each sample is stored in chronological order during one culture experiment in which the culture results of the plurality of samples are determined, wherein the recipe determination device analyzes trends in the culture of each sample based on the interim data for each sample stored in the database device, calculates, for each sample, a posterior probability that indicates the degree of possibility that the parameter values ​​of a plurality of environmental parameters constituting the set recipe will cause future success in the culture of the sample based on a difference between the analysis result of the trend in the culture of the sample and the chronological interim data of the sample, determines one or a plurality of environmental parameters with a relatively high calculated posterior probability as verification parameters, modifies the recipe for each sample by changing the parameter value of the determined verification parameter, and controls the operation of the robotic device so that the robotic device continues to perform a plurality of culture experiments according to the modified recipe.

[0143] Furthermore, a computer-readable tangible non-transitory storage medium having such a program recorded thereon is also an embodiment of the present invention.

[0144] According to such a program or storage medium, one or more computers or processors can read and execute the program, thereby achieving the same effect as the cell culture experimental system of embodiment 1, i.e., determining and implementing the next recipe to be evaluated without waiting for actual experimental results, thereby shortening the time required to obtain an appropriate set of environmental parameters.

[0145] Thus, according to this embodiment, even in the middle of a cell culture experiment (round), the culture tendency of each sample is analyzed based on the progress data obtained up to that point. The system also estimates the probability of successful culture as a posterior probability based on the analysis results, and inputs the estimated posterior probability into the Bayesian estimation formula as the actually obtained experimental result, correcting the recipe for each sample (including parameters related to the robot operation). This processing by the system makes it possible to determine and implement the next recipe to be judged without waiting for the actual experimental results, thereby shortening the time required to obtain an appropriate set of environmental parameters.

[0146] The present invention is not limited to the above-mentioned embodiment, and various modified examples are included. For example, the above-mentioned embodiment has been described in detail to easily explain the present invention, and is not necessarily limited to those having all the configurations described. In addition, it is possible to replace a part of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add the configuration of another embodiment to the configuration of one embodiment. In addition, each of the above-mentioned configurations, functions, processing units, processing means, etc. may be realized in hardware by designing them as integrated circuits, etc. in part or in whole. In addition, each of the above-mentioned configurations, functions, etc. may be realized in software by a processor interpreting and executing a program that realizes each function. Information such as a program, table, file, etc. that realizes each function can be placed in a memory, a recording device such as a hard disk or SSD (Solid State Drive), or a recording medium such as an IC card, SD card, or DVD. [Explanation of symbols]

[0147] 10...cell culture experimental system, 100...control device, 101...operation control unit, 102...detection control unit, 200, 201...terminal device, 300...robot device, 400...detection device, 401...imaging unit, 402...sensor unit, 500...database device, 550...recipe judgment device, 600...cell culture equipment, 601...culture unit, 602...measurement unit, 603...chemical solution installation unit, 661...bottom surface of petri dish

Claims

1. A recipe determination device that sets a recipe to be applied to each of a plurality of cell samples to be cultured; A robot device; a control device that controls the operation of the robot device so that the robot device performs the culture experiment on the plurality of samples according to the set recipe; a database device in which progress data for each of the samples is stored in chronological order during one culture experiment in which the culture results of the samples are determined; The recipe judgment device includes: Analyzing the tendency of the culture of each of the samples based on the progress data of each of the samples stored in the database device; calculating, for each sample, a posterior probability representing the degree of possibility that parameter values ​​of a plurality of environmental parameters constituting the set recipe will cause future success in culturing the sample, based on the analysis result of the tendency in culturing the sample and the difference between the time-series intermediate data of the sample; determining one or more of the environmental parameters for which the calculated posterior probability is relatively high as a verification parameter; modifying a recipe for each sample by changing parameter values ​​of the determined verification parameters; the control device controls the operation of the robotic device so that the robotic device continues to perform the incubation experiment of the plurality of samples according to the modified recipe. Cell culture experimental system.

2. The cell culture experimental system according to claim 1, a detection device for detecting information related to an operation of the robot device, the intermediate progress data includes data representing the detected motion of the robotic device; Cell culture experimental system.

3. The cell culture experimental system according to claim 2, The data representing the operation of the robotic device includes data that can identify at least one of a trajectory of a movement of an instrument handled by the robotic device, a speed of the movement of the instrument, an acceleration of the movement of the instrument, and a posture of the instrument. Cell culture experimental system.

4. The cell culture experimental system according to claim 3, the cells are adherent cells, The operation of the robot device includes a step of peeling off the adherent cells, a step of removing a specimen from a container, or a step of opening and closing a lid of a test tube. Cell culture experimental system.

5. The cell culture experimental system according to claim 2, the detection device includes an imaging unit that records an operation of the robot device; the intermediate progress data includes video data of the operation of the robot device recorded by the imaging unit, Cell culture experimental system.

6. The cell culture experimental system according to claim 1, a detection device for detecting information related to an operation of the robot device, the detection device includes a force sensor that detects a magnitude of a force accompanying an operation of the robot device, the intermediate progress data includes data representing the magnitude of the force detected by the force sensor, Cell culture experimental system.

7. The cell culture experimental system according to claim 6, The force sensor detects pressure when a tool handled by the robot device comes into contact with an object. Cell culture experimental system.

8. The cell culture experimental system according to claim 2, Among the multiple devices constituting the cell culture experimental system, at least the control device, the robot device, and the detection device are synchronized based on a common clock signal. Cell culture experimental system.

9. The cell culture experimental system according to claim 8, The time error representing the accuracy of the clock signal is 10 microseconds or less. Cell culture experimental system.

10. The cell culture experimental system according to claim 1, The recipe judgment device includes: Divide the plurality of samples into a validation group and an efficiency group; The composition of the samples in the validation group and the efficiency group is reset so that the group of samples in which a combination of the type of the environmental parameter and the parameter value that is considered to be highly likely to contribute to the success of cell culture is set based on the posterior probability of the samples has a higher success rate of culture, and the group of samples in which a combination of the type of the environmental parameter and the parameter value that is considered to be highly likely to contribute to the failure of cell culture is set has a lower success rate of culture. Cell culture experimental system.

11. The recipe determination device sets a recipe to be applied to each of a plurality of samples of cells to be cultured, a control device that controls the operation of the robot device so that the robot device performs the culture experiment on the plurality of samples according to the set recipe; the database device stores interim data for each of the samples in chronological order during one culture experiment in which the culture results of the samples are finalized; The recipe judgment device includes: Analyzing the tendency of the culture of each of the samples based on the progress data of each of the samples stored in the database device; calculating, for each sample, a posterior probability representing the degree of possibility that parameter values ​​of a plurality of environmental parameters constituting the set recipe will cause future success in culturing the sample, based on the analysis result of the tendency in culturing the sample and the difference between the time-series intermediate data of the sample; determining one or more of the environmental parameters for which the calculated posterior probability is relatively high as a verification parameter; modifying a recipe for each sample by changing parameter values ​​of the determined verification parameters; the control device controls the operation of the robotic device so that the robotic device continues to perform the incubation experiment of the plurality of samples according to the modified recipe. Cell culture experimental methods.

12. one or more computers or processors, A recipe determination device that sets a recipe to be applied to each of a plurality of cell samples to be cultured; a control device that controls an operation of the robot device so that the robot device performs the culture experiment on the plurality of samples according to the set recipe; A program for causing the device to function as a database device in which progress data for each of the samples is stored in chronological order during one culture experiment in which the culture results of the samples are finalized, The recipe judgment device includes: Analyzing the tendency of the culture of each of the samples based on the progress data of each of the samples stored in the database device; calculating, for each sample, a posterior probability representing the degree of possibility that parameter values ​​of a plurality of environmental parameters constituting the set recipe will cause future success in culturing the sample, based on the analysis result of the tendency in culturing the sample and the difference between the time-series intermediate data of the sample; determining one or more of the environmental parameters for which the calculated posterior probability is relatively high as a verification parameter; modifying a recipe for each sample by changing parameter values ​​of the determined verification parameters; the control device controls the operation of the robotic device so that the robotic device continues to perform the incubation experiment of the plurality of samples according to the modified recipe. program.

Images